Plant leaf identification using Gabor wavelets

Casanova, Dalcimar; Sá, Jarbas Joaci de Mesquita; Bruno, Odemir Martinez

doi:10.1002/ima.20201

Cited by 119 publications

(75 citation statements)

References 17 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This paper presents two contributions. First, we propose a CNN model to automatically learn the features representation for plant categories, replacing the need of designing hand-crafted features as to previous approaches [3,9,12,13]. Second, we identify and diagnose the feature representation learnt by the CNN model through a visualisation strategy based on the DN.…”

Section: Introductionmentioning

confidence: 99%

Deep-plant: Plant identification with convolutional neural networks

Lee

Chan

Wilkin

et al. 2015

2015 IEEE International Conference on Image Processing (ICIP)

360

171

View full text Add to dashboard Cite

This paper studies convolutional neural networks (CNN) to learn unsupervised feature representations for 44 different plant species, collected at the Royal Botanic Gardens, Kew, England. To gain intuition on the chosen features from the CNN model (opposed to a 'black box' solution), a visualisation technique based on the deconvolutional networks (DN) is utilized. It is found that venations of different order have been chosen to uniquely represent each of the plant species. Experimental results using these CNN features with different classifiers show consistency and superiority compared to the state-of-the art solutions which rely on hand-crafted features.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep-plant: Plant identification with convolutional neural networks

Lee

Chan

Wilkin

et al. 2015

2015 IEEE International Conference on Image Processing (ICIP)

360

171

View full text Add to dashboard Cite

show abstract

“…K-means clustering is a supervised learning algorithm and it have a prior knowledge of the number of clusters maximizing intra clustering and Minimizing inter clustering. In the neuronal network is used for sigmoid function [12].Plant species identification requires recognizing the plant by various characteristics, such as size, form, leaf shape, flower color, odor, etc., and linking it with a common or so-called scientific name [8]. The classification algorithm implemented for accurate identification of the plants based on Leaf image.…”

Section: Related Workmentioning

confidence: 99%

Classification of Name Based On Leaf Recognition Using BT and ED Algorithm

A.M.Ravishankkar¹,

Mohanapriya²

2016

IJCATR

View full text Add to dashboard Cite

ABSTRACT:The main purpose of this paper should be to show that the outer frame of a leaf and with the help of Back propagation Network is enough to give a reasonable statement about the species category is identified. Leaves Recognition is a neuronal network based java application/applet to recognize images of leaves using Back propagation Network. The intention is to give the user the ability to administrate a hierarchical list of images, where they can perform some sort of image using edge detection to identify the individual tokens of every image. The Thinning algorithm here is used to process the image recursively and minimizes the found lines to a one-pixel wide one by comparing the actual pixel situation with specific patterns can be identified and then minimizes it. The urgent situation is that due to environmental degradation and lack of awareness, many rare plant species are at the risk of extinction so it is necessary to keep record for plant protection. It focuses on using digital image processing for the purpose of automate classification and recognition of plants based on the images of the leaves. It help to protect the plant and mainly it is used for highly production of rare plant or herbal plant used for medical purpose. Efficacy of the proposed methods is studied by using two neural classifiers. These are neuro-fuzzy controller and a feed-forward back-propagation multi-layered perception to discriminate between 28 classes of leaves. The features have been applied individually as well as in combination to investigate how recognition accuracies can be improved with the help of B&T algorithm.

show abstract

“…Tekstur pada citra digital umumnya dikaitkan pada pengukuran sifat-sifat citra seperti tingkat kekasaran (coarseness), D kehalusan (smoothness) dan keteraturan (regularity). Sehingga tekstur dari citra digital daun dapat dianalisa sebagai keteraturan (regularity) dari pola-pola tertentu tekstur daun [11][12]. Pada penelitian ini, analisa tekstur daun dilakukan pada area permukaan daun yang bukan bagian dari urat daun utama.…”

unclassified

Fitur Berbasis Fraktal Dari Koefisien Wavelet Untuk Klasifikasi Citra Daun

Rakhmadi

Suciati

Navastara

2017

JUTI

View full text Add to dashboard Cite

ABSTRAK ABSTRACT The more numbers and various types of plants in the world make it more difficult to identify and classify plants manually. Leaves are part of a plant that is often used for plant identification and classification. Automatic leaf classification method has been developed by many researchers. In previous research the automatic leaf classification system was built using fractal-based features of fractal dimension and lacunarity. Automatic leaf classification system based on fractal dimensions and lacunarity can classify leaves with high accuracy but require many preprocessing steps resulting in increased system

show abstract

Plant leaf identification using Gabor wavelets

Cited by 119 publications

References 17 publications

Deep-plant: Plant identification with convolutional neural networks

Deep-plant: Plant identification with convolutional neural networks

Classification of Name Based On Leaf Recognition Using BT and ED Algorithm

Fitur Berbasis Fraktal Dari Koefisien Wavelet Untuk Klasifikasi Citra Daun

Contact Info

Product

Resources

About